Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    introducing a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    下列
    0.43
     !",
    0.42
    !!!");
    0.42
    !!!!!!!!
    0.41
    နိုင်သည်။
    0.39
    !!!!!!!!!!!!!!!!
    0.38
    !',
    0.37
     ¡
    0.37
    !!.
    0.36
    !).
    0.36
    POSITIVE LOGITS
    :**
    0.83
    :*
    0.82
    :")
    0.81
    ：
    0.79
    :
    0.79
    :.
    0.77
    :[/
    0.77
    :</
    0.75
    :\
    0.73
    :”
    0.72
    Act Density 0.209%

    No Known Activations